Doubiiu/CodeTalker

Issues

• cal_metric.py error "FileNotFoundError: [Errno 2] No such file or directory: 'RUN/BIWI/CodeTalker_s2/result/npy/F2_e37_condition_F2.npy'"

  #71 opened 2 months ago by bullgokman
  0

• BIWI dataset

  #32 opened 2 years ago by Sylvia-Yuju
  3

• BIWI Dataset Not Available

  #75 opened 7 months ago by ManOfStory
  1

• Evaluation Problem: About the Measuring Unit(mm) and testing

  #70 opened 9 months ago by Tankaishen
  1

• training problem about loss

  #79 opened 4 months ago by renrenzsbbb
  0

• How to plot the analysis graph like the graph in the paper?

  #78 opened 4 months ago by Tankaishen
  0

• How to get the lve.txt and fdd.txt files

  #64 opened a year ago by Shirley-0708
  4

• Render Mean and Std.

  #77 opened 6 months ago by wangryhen
  0

• Can you animate any FLAME face model like voca does

  #45 opened a year ago by GrizzCMX
  8

• render failed

  #76 opened 6 months ago by hrWong
  1

• the input audio file's length limit

  #73 opened 8 months ago by zk19971101
  1

• How to prepare training data ？

  #34 opened 2 years ago by MagicRedZero
  3

• AttributeError: 'tuple' object has no attribute 'transpose'

  #49 opened a year ago by ashutoshbk
  4

• Different training results

  #42 opened a year ago by mhxlearn
  4

• use matlab script to handle the biwi datset

  #74 opened 8 months ago by KangZW-2001
  0

• Add Texuture

  #40 opened 2 years ago by GIT-LZL629
  4

• Is it possible to use facial models trained in Chinese

  #72 opened 8 months ago by huang-1030
  1

• The hidden_states during prediction stage is the same when a custom dataset is used

  #62 opened a year ago by Shirley-0708
  3

• Colab notebook doesn't work

  #50 opened a year ago by epris
  6

• Dont know this technology yet, but Before using it I need to ask a question

  #69 opened a year ago by AIhasArrived
  1

• Code is not present for lip-distance calculations

  #55 opened a year ago by ketyi
  4

• An error occurred while processing long audio using the provided pretrained model.

  #48 opened a year ago by Owen1234560
  5

• 我们创建了一个中文讨论组，有需要的加我微信douzijun1999

  #68 opened a year ago by dousang1999
  0

• ImportErorr

  #33 opened a year ago by Lipolan
  2

• 关于在vocaset上训练meshtalk问题

  #67 opened a year ago by AlongLove
  5

• Is it necessary for commenting out the self.padding_mode != 'zeros'?

  #29 opened a year ago by youngstu
  3

• BIWI dataset preprocess

  #66 opened a year ago by shisuimengli
  1

• About the lve.txt and fdd.txt annotation

  #65 opened a year ago by KVBK01
  0

• the parameters of TCN are fixed, so how to unfreeze

  #61 opened a year ago by Shirley-0708
  2

• a part of biwi data is missing？

  #63 opened a year ago by yangan200203
  2

• psbody module

  #60 opened a year ago by Tinaa23
  3

• A typo in vocaset stage2.yaml? What is "wav_mini"?

  #59 opened a year ago by YifengMa9
  1

• Code about calculating LVE

  #58 opened a year ago by WASD4959
  2

• What is the lip vertex range when calculating LVE?

  #57 opened a year ago by kimhyungkyu-1208
  3

• RuntimeError: The size of the 3D attn_mask is not correct.

  #52 opened a year ago by RujingD
  1

• Not converge when larger batch size is used in Stage2

  #56 opened a year ago by NickChang97
  1

• stage2的训练不收敛

  #54 opened a year ago by RujingD
  1

• How to add natural blinking motions?

  #44 opened a year ago by leetesla
  1

• stage2 training does not converge

  #53 opened a year ago by RujingD
  0

• perplexity

  #51 opened a year ago by RujingD
  3

• No vocabulary dataset found

  #47 opened a year ago by RujingD
  2

• Fail to reproduce on MEAD dataset

  #46 opened a year ago by HarryXD2018
  3

• The lve.txt and fdd.txt files for VOCA were not found

  #43 opened a year ago by liushengtong-nreal
  1

• how to download data_verts.npy, raw_audio_fixed.pkl, templates.pkl and subj_seq_to_idx.pkl?

  #41 opened a year ago by WellTung666
  3

• Real time use ?

  #37 opened 2 years ago by tony-wolff
  1

• how can I implement mean and standard deviation?

  #38 opened 2 years ago by zhengshi119
  1

• my result is not the same as the paper result. why?

  #36 opened 2 years ago by zhengshi119
  2

• Vocaset-test lip sync error comparison results

  #35 opened 2 years ago by khalidhnv
  2

• Can't blink with pretrained model

  #31 opened 2 years ago by kendo6666
  2

• where to get pre-trained models model.pth.tar ?

  #30 opened 2 years ago by MagicRedZero
  8